让大模型零样本搞定跨知识图谱问答，还支持高效扩展。
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
- 用大模型生成关系描述+问题角色初始化，实现零样本泛化。
- 通过分步筛选高连接节点，处理超大规模图仍保持高效。
- 支持大模型迭代追问候选答案、支持事实和推理路径，可控性强。
大型语言模型（LLMs）在推理方面表现优异，但在依赖知识的问题上受限于上下文长度和参数化知识。现有方法依赖微调的LLM或图神经网络检索器，面临数据集特异性微调和在大规模或未见图谱上的可扩展性瓶颈。我们提出LLM-KGFR协同框架，其中结构化检索器知识图谱基础检索器（KGFR）利用大模型生成的关系描述进行编码，并根据问题中的实体角色初始化，实现对未见知识图谱的零样本泛化。为高效处理大规模图谱，采用非对称渐进传播（APP）——逐步扩展过程中选择性限制高阶节点，同时保留有信息量的路径。通过节点级、边级和路径级接口，大模型可迭代请求候选答案、支持事实和推理路径，形成可控的推理循环。实验表明，LLM-KGFR在保持可扩展性和泛化能力的同时实现了强性能，为知识图谱增强推理提供了实用解决方案。
原文摘要 · Abstract (English)
Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. However, existing methods that rely on finetuned LLMs or GNN retrievers are limited by dataset-specific tuning and scalability on large or unseen graphs. We propose the LLM-KGFR collaborative framework, where an LLM works with a structured retriever, the Knowledge Graph Foundation Retriever (KGFR). KGFR encodes relations using LLM-generated descriptions and initializes entities based on their roles in the question, enabling zero-shot generalization to unseen KGs. To handle large graphs efficiently, it employs Asymmetric Progressive Propagation (APP)- a stepwise expansion that selectively limits high-degree nodes while retaining informative paths. Through node-, edge-, and path-level interfaces, the LLM iteratively requests candidate answers, supporting facts, and reasoning paths, forming a controllable reasoning loop. Experiments demonstrate that LLM-KGFR achieves strong performance while maintaining scalability and generalization, providing a practical solution for KG-augmented reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。